Selectic Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Selectic Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP connector for Selectic — give your AI assistant (Claude, ChatGPT, Perplexity, or any MCP-compatible app) the ability to call, text, and email businesses for you: get quotes, book appointments, ask questions — and read back the transcript, recording, and replies. New accounts start with $2 free. US businesses for now.
Most apps can add the hosted endpoint directly as a custom connector:
https://selectic.ai/api/mcpYou'll be prompted to sign in (OAuth) the first time — no API key to manage. For stdio-only clients (e.g. Claude Desktop), this package bridges stdio ↔ the hosted endpoint.
npx -y @selectic/mcp@latestIt opens a browser the first time so you can sign in to Selectic.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"selectic": {
"command": "npx",
"args": ["-y", "@selectic/mcp@latest"]
}
}
}place_call, get_call, send_sms, send_email, get_replies, list_outreach, list_call_types. See https://selectic.ai/docs.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.